Jul 2026· 2026 7th International Conference on Smart Systems and Inventive Technology (ICSSIT)· pp. 1590-1596· 0 citations· 10 references
Abstract
The growing adoption of more sophisticated machine learning models in automated decisioning of credit risks has generated very serious issues of explainability, fairness, and consumer trust, especially when loan applications are denied. Alternative methods of explanation that are available like the use of the static reason codes and traditional counterfactual techniques tend to fail to offer realistic, practical and fair advice to the impacted applicants. In this paper, we present a third-generation counterfactual explain model, which combines structural causal modeling, diffusion-based generative learning, fairness-constrained optimization, and policy adaptability control to produce trustworthy and user-friendly credit clarifications. Actionability and real-world consistency are enforced using a structural causal model to separate mutable and immutable attributes and maintain causal relationships between financial variables. A conditional diffusion network is conditioned on approved credit profiles in order to produce several plausible counterfactual representations of applicants. Such candidates are filtered by original credit model to only keep decision-flipping examples to be valid and are optimized over a multi-objective fairness-constrained formulation that balances small feature changes, realism, and diversity, and demographic equity. Additionally, a policy adaptation module, which is based on reinforcement learning, constantly balances the explanation strategy according to the changing lending policies and regulatory issues. The causal diffusion-based framework proposed had greater counterfactual validity, realism, diversity, and fairness as compared to current gradient-based and heuristic approaches on all of the tested credit datasets.
The rapid adoption of digital technologies has significantly transformed the way banks and financial institutions evaluate loan applications. Machine learning (ML) models are widely used in credit risk assessment to analyze large volumes of financial data and support faster and more reliable lending decisions. However, many of these models operate as black-box systems that provide limited explanation for loan approval or rejection outcomes. In financial environments, where decisions directly impact borrowers and institutional risk exposure, lack of transparency may reduce trust and raise concerns regarding fairness and accountability. To address these challenges, this study proposes a Transparent and Explainable Artificial Intelligence (XAI) framework for risk-aware loan approval decision support. The proposed framework integrates predictive modeling with explainability techniques such as SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), Counterfactual Explanations, and Permutation Feature Importance. These techniques provide both global insights into model behavior and clear explanations for individual loan decisions. In addition, fairness evaluation mechanisms are incorporated to detect potential bias across sensitive attributes. Experimental results demonstrate that integrating explainability improves transparency and user confidence while maintaining strong predictive performance, thereby supporting reliable and responsible AI-based loan approval systems for financial institutions.
Ch.Padma, N. Bhavani, G. Prakash et al.· 2026 4th International Confe...· 0 citations
Fairness and bias concerns in AI systems arise when predictive models amplify inequities present in data, and measurement processes. Traditional fairness analysis approaches such as demographic parity, equalized odds, and individual fairness primarily operate on statistical associations and often struggle when protected attributes influence features through complex causal pathways. This paper explores causal inference modelling for identification and mitigation of fairness and bias issues in AI system. The proposed framework integrates structural causal models (SCMs) with an explainable AI method, Shapley Additive Explanations (SHAP) to provide interpretations to the AI system outcomes. The framework introduces structural causal modelling with counterfactual queries for the analysis of sources of fairness and bias through the protected variables. The framework is experimented on a synthetic loan application dataset with the results showing the effects of protected attributes (race and gender) on credit approval rates. The models also achieve average AUC score of 70% on the dataset.
A. Adegun, Wei Li, Samuel Fawale· IEEE International Conferenc...· 0 citations
Algorithmic credit scoring must satisfy fairness and explanation requirements, yet prevailing predictive-parity criteria assess only outcomes at the decision point. They can therefore overlook whether rejected applicants face unequal burdens in reaching future approval, a phenomenon we call masked inequality. We develop an effort-centric framework that measures an applicant's effort as the minimum weighted cost of feasible changes required to cross the approval boundary. The framework distinguishes feature-independent actions from additive structural shifts that propagate through a causal model and defines parity by comparing average minimum effort across protected groups. We derive tractable local expressions for general differentiable classifiers and exact expressions for logistic regression, embed them in an in-processing fairness objective, and bound changes in portfolio credit risk. The same optimisation yields actionable pathways to approval. Using mortgage data with continuous and discrete features, we find that rejected female applicants require greater effort even when standard predictive-parity criteria are satisfied. Feature-independent regularisation reduces the effort gap by more than 50\% with modest predictive changes. Causal regularisation yields reductions above 90\% at the tested positive penalty weights, but with larger predictive and risk-return trade-offs. Expected and unexpected losses remain broadly stable under feature-independent regularisation and increase under causal regularisation; RAROC declines but remains positive. These results show that effort parity complements predictive fairness by revealing and mitigating hidden barriers to future credit access while making the associated operational trade-offs explicit.
Carbon-crediting methodologies determine how imperfect monitoring, reporting, and verification (MRV) evidence is translated into issued credits. When project developers can influence measured outcomes, greater reliance on project-specific data improves targeting but also strengthens incentives to manipulate the signal. We develop a model in which a crediting authority commits to a crediting rule while anticipating the project developer's response. The framework distinguishes statistical accuracy from gaming robustness. The optimal rule generally attenuates the MRV signal: greater accuracy and robustness justify stronger reliance on project-specific evidence, whereas higher credit prices and greater heterogeneity in gaming ability call for a flatter rule. Even when manipulation becomes prohibitively difficult, measurement noise alone implies attenuation. We also characterize how market and project conditions affect the relative value of improving accuracy versus robustness. An illustration using project-level data on cookstove carbon credits shows how independent reassessments can inform the framework and highlights the data requirements for empirical implementation.
Daniel Heyen, Frederik Holtel· CESifo working papers· 0 citations
Findr, short for flexible, interpretable deep regression, is introduced, a semi-structured framework for binary credit risk modelling that decomposes the logit into an interpretable structured component and an orthogonal neural residual.
Victor Medina-Olivares, Stefan Lessmann, Jonathan Crook· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
